中国物理B ›› 2025, Vol. 34 ›› Issue (12): 127301-127301.doi: 10.1088/1674-1056/adfefb

• • 上一篇    下一篇

Brain-inspired memristive pooling method for enhanced edge computing

Wenbin Guo(郭文斌)†, Zhe Feng (冯哲)†, Haochen Wang (王昊辰), Zhihao Lin(蔺志豪), Jianxun Zou(邹建勋), Zuyu Xu(徐祖雨), Yunlai Zhu(朱云来)‡, Yuehua Dai (代月花)§, and Zuheng Wu (吴祖恒)   

  1. School of Integrated Circuits, Anhui University, Hefei 230601, China
  • 收稿日期:2025-06-24 修回日期:2025-08-25 接受日期:2025-08-26 发布日期:2025-12-04
  • 通讯作者: Yunlai Zhu, Yuehua Dai, Zuheng Wu E-mail:zhuyunlai@ahu.edu.cn;daiyuehua@ahu.edu.cn;wuzuheng@ahu.edu.cn
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62274002, 62304001, and 62201005), the Anhui Provincial Natural Science Foundation (Grant Nos. 2308085QF213 and 2408085QF211), and the Natural Science Research Project of the Anhui Educational Committee (Grant No. 2023AH050072).

Brain-inspired memristive pooling method for enhanced edge computing

Wenbin Guo(郭文斌)†, Zhe Feng (冯哲)†, Haochen Wang (王昊辰), Zhihao Lin(蔺志豪), Jianxun Zou(邹建勋), Zuyu Xu(徐祖雨), Yunlai Zhu(朱云来)‡, Yuehua Dai (代月花)§, and Zuheng Wu (吴祖恒)   

  1. School of Integrated Circuits, Anhui University, Hefei 230601, China
  • Received:2025-06-24 Revised:2025-08-25 Accepted:2025-08-26 Published:2025-12-04
  • Contact: Yunlai Zhu, Yuehua Dai, Zuheng Wu E-mail:zhuyunlai@ahu.edu.cn;daiyuehua@ahu.edu.cn;wuzuheng@ahu.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62274002, 62304001, and 62201005), the Anhui Provincial Natural Science Foundation (Grant Nos. 2308085QF213 and 2408085QF211), and the Natural Science Research Project of the Anhui Educational Committee (Grant No. 2023AH050072).

PDF (PC)

0

赞

摘要： Edge deployment solutions based on convolutional neural networks (CNNs) have garnered significant attention because of their potential applications. However, traditional CNNs rely on pooling to reduce the feature size, leading to substantial information loss and reduced network robustness. Herein, we propose a more robust adaptive pooling network (APN) method implemented using memristor technology. Our method introduces an improved pooling layer that reduces input features to an arbitrary scale without compromising their importance. Different coupling coefficients of the pooling layer are stored as conductance values in arrays. We validate the proposed APN on generic datasets, demonstrating significant performance improvements over previously reported CNN architectures. Additionally, we evaluate the APN on a CAPTCHA recognition task with perturbations to assess network robustness. The results show that the APN achieves 92.6% accuracy in 4-digit CAPTCHA recognition and exhibits higher robustness. This brief presents a highly robust and novel scheme for edge computing using memristor technology.

关键词: memristor, edge computing, adaptive pooling, image classification

Abstract: Edge deployment solutions based on convolutional neural networks (CNNs) have garnered significant attention because of their potential applications. However, traditional CNNs rely on pooling to reduce the feature size, leading to substantial information loss and reduced network robustness. Herein, we propose a more robust adaptive pooling network (APN) method implemented using memristor technology. Our method introduces an improved pooling layer that reduces input features to an arbitrary scale without compromising their importance. Different coupling coefficients of the pooling layer are stored as conductance values in arrays. We validate the proposed APN on generic datasets, demonstrating significant performance improvements over previously reported CNN architectures. Additionally, we evaluate the APN on a CAPTCHA recognition task with perturbations to assess network robustness. The results show that the APN achieves 92.6% accuracy in 4-digit CAPTCHA recognition and exhibits higher robustness. This brief presents a highly robust and novel scheme for edge computing using memristor technology.

Key words: memristor, edge computing, adaptive pooling, image classification

中图分类号:  (Metal-semiconductor-metal structures)

  • 73.40.Sx
84.35.+i (Neural networks) 07.05.Pj (Image processing) 87.19.lv (Learning and memory)